ACIT4030 Machine Learning for 3D Computer Vision Course description

This course will present the state of the art in algorithms for machine learning on images and 3D data. After a brief introduction to image processing and 3D geometry, we will cover topics within both supervised and unsupervised learning. The course covers classical problems like classification, segmentation, and correspondence detection. Recent work on shape and image synthesis will also be discussed. We will in particular study deep neural architectures for 2D images and 3D data such as point clouds and shape graphs. Additionally, 3D shape design with generative models will be presented.

ndividual written and oral exams will be held at the end of the spring semester. The student gets two separate grades, one for the written and one for the oral exam, and the exams can be taken again separately. The written exam counts 53% of the final grade and the oral exam counts 47%.

Written exam (6 hours) consisting of three parts:

• a Norwegian-English translation and vocabulary exercise
• a text for comprehension and analysis, and questions from the syllabus in English for Business Studies
• an essay on a topic from American and/or British society

Oral exam (20 minutes) consisting of:

• presentation of a topic from American and/or British society
• discussion/reflection on one of the cases, a work of fiction or selected texts called 'American Perspectives' or 'British Perspectives'.

Both exams must be passed in order to pass the course.

No formal requirements over and above the admission requirements.

Upon successful completion of the course, the candidate:

Knowledge

• has knowledge of classical problems within graphics and imaging that are applicable to machine learning, such as classification, segmentation, and correspondence detection.
• has a good understanding of problems related to generation of new images and 3D shapes.

Skills

• is able to apply state-of-the art machine learning algorithms to real-world problems related to imaging and 3D graphics.

Competence

• is aware of the state of the art in algorithms for machine learning on images and 3D data.
• has experience with real world problems within the course domain, with a focus on solutions using deep neural architectures.

Teaching approach is a combination of traditional weekly lectures and assignments, student- led seminars, and a final project. Lectures will present the core theory of the course content and homework will focus on theoretical knowledge. In student-led seminars, topical research papers will be presented and discussed. The final project exposes the student to a chosen real- world problem relevant to the course topic.

Practical training

The student will be exposed to programming with repositories such as ImageNet and ShapeNet and will have created solutions for real-world problems related to data-driven graphics and imaging.

The main purpose of the course is to improve the students' ability to communicate in English both in writing and orally in a professional context. The course is cross-curricular since a large part of the syllabus is related to subjects within business and economics. It will prepare the students to deal with real situations in the business world.

No prerequisites.

All printed and written aids and a calculator that cannot be used to communicate with others.

The teaching consists of about 110 periods, 55 in the autumn semester and 55 in the spring semester.

In addition to lectures there are case studies, group work, assignment review, discussions, student presentations, and written assignments. Regular attendance and active participation in classroom activities are expected. Independent study is required.

The following assignments are obligatory:

Autumn semester:

- One short (300-500 words) written assignment based on one of the cases (attendance is mandatory for the case the student writes about)

- An essay, approximately 500 words, on an assigned topic

- An individual 7-minute oral presentation

Spring semester

- One short (300-500 words) written assignment based on one of the cases (attendance is mandatory for the case the student writes about)

- An essay, approximately 500 words, on an assigned topic

- A major oral group project

Feedback will be given on all assignments. The essays must adhere to the rules established in -Mal for oppgaveskriving ved SAM- (available on the SAM home pages). In order to take the final exam, all obligatory assignments must be approved by the instructor. Students will be given the opportunity to re-submit obligatory assignments that have not been approved. If assignments are not approved after re-submission(s), students will not be allowed to take the exam.